Journals / Sosyal Bilimler Araştırma Dergisi / 2021 / Cilt: 10 - Sayı: 1

Determination of COVID-19 Diagnosis with Discriminant Analysis and Artificial Neural Networks According to Blood Test Results

Kan Tahlili Sonuçlarına Göre Diskriminant Analizi ve Yapay Sinir Ağları ile Covid-19 Teşhisinin Belirlenmesi

Pages
221–232
Publication Date
2021-03-29
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

According to this result, it was determined that the model created with artificial neural networks is more successful than discriminant analysis in predicting positive patients.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:On December 31, 2019, 27 pneumonia cases of unknown type were detected in China's Wuhan city, Hubei province.
📊
Key Findings & Data:On January 30, 2020, World Health Organization (WHO) declared the Coronavirus Disease (COVID)-19 outbreak in China as a Public Health Emergency of International Concern, posing a high risk for countries with vulnerable health systems.
💡
Conclusion & Impact:According to this result, it was determined that the model created with artificial neural networks is more successful than discriminant analysis in predicting positive patients.
🔬Design:Modeling & Simulation
📍Scope:2019 Verileri
⚙️Variables:COVID-19 · Diskrminant Analizi · Hastalık Teşhisi

Abstract

On December 31, 2019, 27 pneumonia cases of unknown type were detected in China's Wuhan city, Hubei province. On January 30, 2020, World Health Organization (WHO) declared the Coronavirus Disease (COVID)-19 outbreak in China as a Public Health Emergency of International Concern, posing a high risk for countries with vulnerable health systems. Samples taken from the upper respiratory tract and lower respiratory tract are used in the diagnosis of COVID-19. In this study, it was aimed to provide a method that could be an alternative to Reverse Transcription-Polymerase Chain Reaction RT-PCR test, to create a more reliable diagnostic method than the 60% accurate diagnosis rate of RT-PCR test, and to determine whether COVID-19 could be diagnosed by only blood analysis without taking a swab sample from the upper respiratory tract. Hematocrit, hemoglobin, mean platelet volume, red blood cell count and RT-PCR test results of 159 patients who had RT-PCR test at Hospital Sírio-Libanês in São Paulo, Brazil were used in the study. Discriminant analysis and artificial neural network models were used in the diagnosis of COVID-19 of the patients. As a result of the study, discriminant analysis was 89.9% successful, and artificial neural networks were 93.7% successful. According to this result, it was determined that the model created with artificial neural networks is more successful than discriminant analysis in predicting positive patients.

Özet

31 Aralık 2019’da tipi bilinmeyen 27 zatürre vakası Çin’in Hubei eyaleti, Wuhan şehrinde tespit edilmiştir. 30 Ocak 2020’de WHO, Çin’deki COVID-19 salgınını, savunmasız sağlık sistemlerine sahip ülkeler için yüksek risk oluşturan Uluslararası Öneme Sahip Halk Sağlığı Acil Durumu olarak ilan etmiştir. COVID-19 hastalığının teşhisinden üst solunum yollarından ve alt solunum yollarından alınan örnekler kullanılmaktadır. Bu çalışmada RT-PCR testine alternatif olabilecek bir yöntem sunabilmek, RT-PCR testinin %60 doğru teşhis oranından daha güvenilir bir teşhis yöntemi oluşturmak ve üst solunum yollarından süprüntü örneği almadan sadece kan tahlili ile COVID-19’un teşhis edip edilemeyeceğinin tespit edilmesi amaçlanmıştır. Çalışmada São Paulo, Brezilya’daki Israelita Albert Einstein Hastanesinde RT-PCR testi yaptırmış 159 hastanın Hemotokrit, Hemoglobin, Ortalama Trombosit Hacmi, Kırmızı Kan Hücresi Sayısı ve RT-PCR testi sonuçlarından yararlanılmıştır. Hastaların COVID-19 teşhisinde diskriminant analizi ve yapay sinir ağları modelleri kullanılmıştır. Çalışmanın sonucunda diskriminant analizi %89,9, yapay sinir ağları ise %93,7 oranında başarılı olmuşlardır. Yapay sinir ağları ile oluşturulan modelin pozitif hastaları tahmin etmede diskriminant analizine göre daha başarılı olduğu tespit edilmiştir.

🔖

Cite This Article

ÖZDEN, Ü. H., ERİŞLİK, K. (2021). Determination of COVID-19 Diagnosis with Discriminant Analysis and Artificial Neural Networks According to Blood Test Results. Sosyal Bilimler Araştırma Dergisi, Cilt: 10 - Sayı: 1, 221–232. https://ajindex.com/articles/801563

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (10)

  1. Alpar, R. (2017). Uygulamalı çok değişkenli istatistiksel yöntemler. Detay Yayıncılık. Brauner, N., & Shacham, M. (1999). Regression diagnostic using an orthogonalized variables based stepwise regression procedure. Computers & Chemical Engineering, 23, S327-S330. https://doi.org/10.1016/S0098-1354(99)80080-5
  2. Chen, N., Zhou, M., Dong, X., Qu, J., Gong, F., Han, Y., Qiu, Y., Wang, J., Liu, Y., Wei, Y., Xia, J., Yu, T., Zhang, X., & Zhang, L. (2020). Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: A descriptive study. The Lancet, 395(10223), 507-513. https://doi.org/10.1016/S0140-6736(20)30211-7
  3. Cheng, B., & Titterington, D. M. (1994). Neural Networks: A Review from a Statistical Perspective. Statistical Science, 9(1), 2-30. https://doi.org/10.1214/ss/1177010638
  4. Cilimkovic, M. (2010). Neural Networks and Back Propagation Algorithm. Elmas, Ç. (2011). Yapay zeka uygulamaları: (Yapay sinir ağı, bulanık mantık, genetik algoritma). Seçkin Yayıncılık. Fraley, C., & Raftery, A. E. (2002).
  5. Model-Based Clustering, Discriminant Analysis, and Density Estimation. Journal of the American Statistical Association, 97(458), 611-631. https://doi.org/10.1198/016214502760047131
  6. Gholamy, A., Kreinovich, V., & Kosheleva, O. (2018). Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation. Hazarika, A., Dutta, L., Barthakur, M., & Bhuyan, M. (2019). A Multiview Discriminant Feature Fusion-Based Nonlinear Process Assessment and Diagnosis: Application to Medical Diagnosis. IEEE Transactions on Instrumentation and Measurement, 68(7), 2498-2506. https://doi.org/10.1109/TIM.2018.2866744
  7. Heydari, S. T., Ayatollahi, S. M. T., & Zare, N. (2012). Comparison of Artificial Neural Networks with Logistic Regression for Detection of Obesity. Journal of Medical Systems, 36(4), 2449-2454. https://doi.org/10.1007/s10916-011-9711-4
  8. Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359-366. https://doi.org/10.1016/0893-6080(89)90020-8
  9. Huang, C., Wang, Y., Li, X., Ren, L., Zhao, J., Hu, Y., Zhang, L., Fan, G., Xu, J., Gu, X., Cheng, Z., Yu, T., Xia, J., Wei, Y., Wu, W., Xie, X., Yin, W., Li, H., Liu, M., … Cao, B. (2020). Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. The Lancet, 395(10223), 497-506. https://doi.org/10.1016/S0140-6736(20)30183-5
  10. Kujawski, S. A., Wong, K. K., Collins, J. P.,